{"id":"https://openalex.org/W4410808570","doi":"https://doi.org/10.1109/tcsvt.2025.3574499","title":"Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning","display_name":"Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W4410808570","doi":"https://doi.org/10.1109/tcsvt.2025.3574499"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3574499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3574499","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046442204","display_name":"Wenrui Li","orcid":"https://orcid.org/0000-0002-2393-9016"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Li","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-2393-9016","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033038967","display_name":"Penghong Wang","orcid":"https://orcid.org/0000-0002-5401-5676"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penghong Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-5401-5676","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022103187","display_name":"Xingtao Wang","orcid":"https://orcid.org/0000-0002-5763-2493"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingtao Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-5763-2493","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3330-783X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-9660-3636","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["School of AI for Science and the Shenzhen Graduate School, Peking University, Shenzhen, China","School of Electronics and Computer Engineering and the School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2978-5935","affiliations":[{"raw_affiliation_string":"School of AI for Science and the Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628","https://openalex.org/I20231570","https://openalex.org/I180726961"]},{"raw_affiliation_string":"School of Electronics and Computer Engineering and the School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.8254,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96917151,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"35","issue":"11","first_page":"10772","last_page":"10786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5733287334442139},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49557650089263916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47059810161590576},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4508419632911682},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4504771828651428},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4440648853778839},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12076723575592041},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11478248238563538},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10094603896141052},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08286207914352417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5733287334442139},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49557650089263916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47059810161590576},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4508419632911682},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4504771828651428},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4440648853778839},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12076723575592041},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11478248238563538},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10094603896141052},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08286207914352417}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3574499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3574499","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3596121031","display_name":null,"funder_award_id":"HIT.DZJJ.2024025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4587952244","display_name":null,"funder_award_id":"62027804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5151253548","display_name":null,"funder_award_id":"62332002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5410805085","display_name":null,"funder_award_id":"62402138","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7374398270","display_name":null,"funder_award_id":"HIT.DZJJ.2024025","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8685418503","display_name":null,"funder_award_id":"624B2049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W2016053056","https://openalex.org/W2044913453","https://openalex.org/W2125949049","https://openalex.org/W2171061940","https://openalex.org/W2513853720","https://openalex.org/W2526050071","https://openalex.org/W2590382526","https://openalex.org/W2703895418","https://openalex.org/W2785582094","https://openalex.org/W2799215068","https://openalex.org/W2890236183","https://openalex.org/W2924476266","https://openalex.org/W2938463073","https://openalex.org/W2963283377","https://openalex.org/W2963545832","https://openalex.org/W2963960318","https://openalex.org/W2969884493","https://openalex.org/W2997217064","https://openalex.org/W2998281665","https://openalex.org/W3013427177","https://openalex.org/W3015371781","https://openalex.org/W3025520547","https://openalex.org/W3109728025","https://openalex.org/W3119136678","https://openalex.org/W3138521398","https://openalex.org/W3139658937","https://openalex.org/W3173623687","https://openalex.org/W3200729277","https://openalex.org/W4285124932","https://openalex.org/W4297697565","https://openalex.org/W4312653797","https://openalex.org/W4312763854","https://openalex.org/W4313477296","https://openalex.org/W4362562911","https://openalex.org/W4362654522","https://openalex.org/W4386065852","https://openalex.org/W4386072365","https://openalex.org/W4386159996","https://openalex.org/W4387247768","https://openalex.org/W4387885896","https://openalex.org/W4387969040","https://openalex.org/W4389065381","https://openalex.org/W4389104669","https://openalex.org/W4389371479","https://openalex.org/W4390871729","https://openalex.org/W4390872378","https://openalex.org/W4391582647","https://openalex.org/W4392796720","https://openalex.org/W4396918399","https://openalex.org/W4400903918","https://openalex.org/W4403758862"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Audio-visual":[0],"zero-shot":[1],"learning":[2,57],"(ZSL)":[3],"has":[4],"been":[5],"extensively":[6],"researched":[7],"for":[8],"its":[9],"capability":[10],"to":[11,61,73,83,104],"classify":[12],"video":[13],"data":[14],"from":[15],"unseen":[16],"classes":[17],"during":[18],"training.":[19],"Nevertheless,":[20],"current":[21],"methodologies":[22],"often":[23],"struggle":[24],"with":[25],"background":[26,94],"scene":[27,95],"biases":[28],"and":[29,49,66,92,118,134,158,164,169],"inadequate":[30],"motion":[31,52,88,107,119,133,157],"detail.":[32],"This":[33],"paper":[34],"proposes":[35],"a":[36,100],"novel":[37],"dual-stream":[38],"Multi-Timescale":[39],"Motion-Decoupled":[40],"Spiking":[41],"Transformer":[42],"(MDST++),":[43],"which":[44],"decouples":[45],"contextual":[46,63,135],"semantic":[47,64,136],"information":[48,65,89,160],"sparse":[50],"dynamic":[51],"information.":[53,108,137],"The":[54],"recurrent":[55],"joint":[56,68],"unit":[58],"is":[59],"proposed":[60],"extract":[62],"capture":[67],"knowledge":[69],"across":[70],"various":[71],"modalities":[72],"understand":[74],"the":[75,111,124,141],"environment":[76],"of":[77,113,126,143],"actions.":[78],"By":[79],"converting":[80],"RGB":[81],"images":[82],"events,":[84],"our":[85],"method":[86],"captures":[87],"more":[90],"accurately":[91],"mitigates":[93],"biases.":[96],"Moreover,":[97],"we":[98,121],"introduce":[99],"discrepancy":[101],"analysis":[102],"block":[103],"model":[105],"audio":[106],"To":[109],"enhance":[110],"robustness":[112],"SNNs":[114],"in":[115],"extracting":[116],"temporal":[117],"cues,":[120],"dynamically":[122],"adjust":[123],"threshold":[125],"Leaky":[127],"Integrate-and-Fire":[128],"neurons":[129],"based":[130],"on":[131,152],"global":[132],"Our":[138],"experiments":[139],"validate":[140],"effectiveness":[142],"MDST++,":[144],"demonstrating":[145],"their":[146],"consistent":[147],"superiority":[148],"over":[149],"state-of-the-art":[150],"methods":[151],"mainstream":[153],"benchmarks.":[154],"Additionally,":[155],"incorporating":[156],"multi-timescale":[159],"significantly":[161],"improves":[162],"HM":[163],"ZSL":[165],"accuracy":[166],"by":[167],"26.2%":[168],"39.9%.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}